iA-HLD: an improved AlexNet for hairline fracture detection in orthopedic images DOI
Bhawna Jain,

Diksha Malik,

Ganiti Jagota

и другие.

Neural Computing and Applications, Год журнала: 2024, Номер unknown

Опубликована: Окт. 1, 2024

Язык: Английский

Authenticating and securing healthcare records: A deep learning-based zero watermarking approach DOI
Ashima Anand, Jatin Bedi, Ashutosh Aggarwal

и другие.

Image and Vision Computing, Год журнала: 2024, Номер 145, С. 104975 - 104975

Опубликована: Март 12, 2024

Язык: Английский

Процитировано

18
Recent advancements and applications of deep learning in heart failure: Α systematic review DOI
Georgios Petmezas, Vasileios E. Papageorgiou,

Vasileios Vassilikos

и другие.

Computers in Biology and Medicine, Год журнала: 2024, Номер 176, С. 108557 - 108557

Опубликована: Май 7, 2024

Язык: Английский

Процитировано

13
Transfer learning by fine-tuning pre-trained convolutional neural network architectures for switchgear fault detection using thermal imaging DOI Creative Commons

Karim A.A. Mahmoud,

Mohamed M. Badr,

Noha A. Elmalhy

и другие.

Alexandria Engineering Journal, Год журнала: 2024, Номер 103, С. 327 - 342

Опубликована: Июнь 18, 2024

Язык: Английский

Процитировано

5
A review of artificial intelligence in wound care DOI Open Access

Ovya Ganesan,

Miranda X. Morris,

Lifei Guo

и другие.

Artificial Intelligence Surgery, Год журнала: 2024, Номер 4(4), С. 364 - 75

Опубликована: Ноя. 4, 2024

Our aging population, diabetes, and obesity have fueled the growth of chronic wounds seen throughout world. Often, are a marker poor health that leads to increased mortality rates. However, diagnosis treatment these challenging. Incorrectly differentiating between other complex conditions can lead adverse events. Artificial intelligence (AI) has been shown offer some early benefits, we hypothesized it may enhance wound care but also carry notable risks. We performed detailed search using PubMed, Scopus, Cumulated Index in Nursing Allied Health Literature, Web Science for AI applications care. was found be applied characterization, monitoring tissue change, daily therapy, prevention prognostics. made more efficient accurate assessments, less painful assessments wounds, personalized treatment, improved prognostic prediction capabilities. allowed precise at-home observation care, facilitating earlier as needed. Challenges associated with included how best allocate AI-assisted technologies equitably, safely maintain patient data, diversify datasets algorithm training. Because algorithms not transparent, validating findings presents powerful tool several aspects advanced potential improve diagnoses, accelerate healing, reduce pain, cost-effectiveness More research needs done into incorporate clinical practice while keeping clinicians aware risks evolving technologies.

Язык: Английский

Процитировано

4
Innovative fusion of VGG16, MobileNet, EfficientNet, AlexNet, and ResNet50 for MRI-based brain tumor identification DOI

Marjan Kia,

Soroush Sadeghi,

Homayoun Safarpour

и другие.

Iran Journal of Computer Science, Год журнала: 2024, Номер unknown

Опубликована: Дек. 9, 2024

Язык: Английский

Процитировано

4
Transfer of learning in convolutional neural networks for thermal image classification in Electrical Transformer Rooms DOI Creative Commons

Abdallah A. Elgohary,

Mohamed M. Badr,

Noha A. Elmalhy

и другие.

Alexandria Engineering Journal, Год журнала: 2024, Номер 105, С. 423 - 436

Опубликована: Авг. 9, 2024

Overheating of power transformers, low-voltage panels, and medium-voltage components in Electric Transformer Rooms (ETRs) can result from various factors, such as contact issues, irregular loads, other similar problems. Thermal imaging shows significant potential for detecting faults equipment. However, its effectiveness is hindered by the complex thermal patterns variability equipment environmental conditions, making accurate fault detection challenging. This paper aims to study transfer learning architectures automating classification ETRs. work applies four architectures: AlexNet, SqueezeNet, VGG19, GoogLeNet. The findings testing phase demonstrated that use fine-tuning pre-trained convolutional neural networks was highly effective images captured ETRs, with models achieving accuracy rates between 86.98% 100%, F 1 -Scores 86.79% 100%. • Transfer applied automate A dataset set up augmented improve generalization abilities proposed models. Establish standard comparisons among architectures.

Язык: Английский

Процитировано

3
Performance evaluation of pretrained deep learning architectures for railway passenger ride quality classification DOI
Aliyu Kasimu, Wei Zhou, Qingkai Meng

и другие.

Alexandria Engineering Journal, Год журнала: 2025, Номер 118, С. 194 - 207

Опубликована: Янв. 22, 2025

Язык: Английский

Процитировано

0
A Deep Learning Model Based on RGB and Hyperspectral Images for Efficiently Detecting Tea Green Leafhopper Damage Symptoms DOI Creative Commons
Yang Xu,

Yilin Mao,

He Li

и другие.

Smart Agricultural Technology, Год журнала: 2025, Номер unknown, С. 100817 - 100817

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0
Application of Improved VGG Net in Metallographic Recognition DOI
Fei Gao, Denghui Wang, Zheng Zhang

и другие.

Опубликована: Янв. 10, 2025

Язык: Английский

Процитировано

0
An image segmentation method using intuitionistic fuzzy k-means and convolutional neural networks in multiclass image classification DOI

Potharla Ramadevi,

Raja Das,

M. Lakshmi

и другие.

Elsevier eBooks, Год журнала: 2025, Номер unknown, С. 111 - 129

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0